Answers are grounded in this paper and cite their sources.
Background The CheckPD app combines a 20-item symptom questionnaire with smartphone sensor and voice assessments. We evaluated the questionnaire as a first-stage triage component and explored the contribution of digital features. Methods A hospital case-control evaluation included 60 participants with Parkinson’s disease (PD) and 107 volunteer controls. Community screening included 1,510 participants; those meeting questionnaire or app referral criteria underwent specialist assessment. In a subgroup of 78 clinically evaluated participants, three prespecified model families were compared using questionnaire-only (Q) and questionnaire-plus-sensor (Q + S) features with matched participant-level five-fold cross-validation. Results In the hospital cohort, the questionnaire showed strong apparent discrimination (area under the receiver operating characteristic curve [ROC-AUC] 0.971, 95% confidence interval [CI] 0.951–0.992). A score of at least 5 yielded 90.00% sensitivity and 93.46% specificity. Each additional positive response was associated with higher odds of PD status after adjustment for age and sex (adjusted odds ratio 1.853, 95% CI 1.464–2.344). In community screening, 43 of 98 questionnaire-positive participants had confirmed PD (positive predictive value 43.88%; detection yield 2.85%). The app-based pathway identified four additional cases below the questionnaire threshold, giving 47 cases overall (3.11%). Mean ROC-AUC was higher with Q + S than with Q across all three models. Conclusions The questionnaire showed strong apparent hospital discrimination but more modest community performance. It should be used as a first-stage triage component within, rather than as a replacement for, the multimodal CheckPD pathway. External validation with blinded assessment and verification of screen-negative participants is required.
No takes yet. Share an insight, caveat, or question.
Sringean et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: